Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1975. Min Act: -0.0000

Data Index: 368741 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1709. Min Act: -0.0000

Data Index: 535200 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1713. Min Act: -0.0000

Data Index: 497518 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1773. Min Act: -0.0000

Data Index: 451959 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1659. Min Act: -0.0000

Data Index: 606819 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1346265 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1653. Min Act: -0.0000

Data Index: 778184 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1699. Min Act: -0.0000

Data Index: 495360 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1636. Min Act: -0.0000

Data Index: 355221 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1625. Min Act: -0.0000

Data Index: 934886 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1558. Min Act: -0.0000

Data Index: 955304 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1605. Min Act: -0.0000

Data Index: 715478 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1162898 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1133323 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1487. Min Act: -0.0000

Data Index: 938235 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1534. Min Act: -0.0000

Data Index: 645931 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1450. Min Act: -0.0000

Data Index: 287573 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1493. Min Act: -0.0000

Data Index: 435021 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1031708 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1588. Min Act: -0.0000

Data Index: 512280 (C4 (Web Text))

Max Activating Token Index: 139